design-handoff-spec

design-handoff-spec is a skill for Claude Code, Codex from makifbaysal/tasktrooper. It costs 51 tokens per session (1,565 once invoked), scanned A, original, Apache-2.0.

A hand-off document for turning an approved screen design into working software. It records the components, design values, text, states, responsive behaviour at different screen widths, and accessibility requirements that implementers should follow.

In plain words
What is it for?
Use it after a design is approved and before implementation, for screens such as invoice lists, forms, and other interfaces with multiple states and layouts.
Why use it?
It prevents developers from having to guess details that may be missing from a visual mock-up or lost when the design is passed through another system.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it after a design is approved and before implementation, for screens such as invoice lists, forms, and other interfaces with multiple states and layouts.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/makifbaysal/tasktrooper/design-handoff-spec
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add makifbaysal/tasktrooper --skill design-handoff-spec
Clone the repo
git clone --depth 1 https://github.com/makifbaysal/tasktrooper

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for design-handoff-spec

README.md
[![agentmods](https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/design-handoff-spec/github.svg)](https://agentmods.dev/skills/makifbaysal/tasktrooper/design-handoff-spec)
Your own site
<a href="https://agentmods.dev/skills/makifbaysal/tasktrooper/design-handoff-spec"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/design-handoff-spec/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for design-handoff-spec

Your own site · 80×15
<a href="https://agentmods.dev/skills/makifbaysal/tasktrooper/design-handoff-spec"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/design-handoff-spec.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,565 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00051 $0.01565
Opus 5.5 $0.00020 $0.00626
Sonnet 5.5 $0.00010 $0.00313
Haiku 4.5 $0.00005 $0.00156

Measured 4d ago against content hash 1f88c1bec0ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

design-handoff-spec scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

catalog/agents/ui-designer/skills/design-handoff-spec/SKILL.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design Hand-off Spec

Overview

Every task blocked by this design task receives its documents in its run context as TEXT, under "## The approved design this task builds" — the hand-off specs first, then every mockup, the variants that were not chosen included. The markup of a mockup is dropped, so its colours, sizes and layout do not survive the trip. The hand-off spec is what they can act on. It is written after approval, from the chosen variant only, and it names things — components, tokens, copy — instead of describing pixels.

Core principle: An implementer reading only this spec builds the approved screen without inventing a single value, string or state.

Shape

One markdown document per screen, attached in the done run with add_task_document, titled handoff: <screen> — the same <screen> as its design: <screen> · <letter> mockups. Under ~10,000 characters: a markdown document reaches a dependent's run cut at 12,000, and the end is what gets cut.

# handoff: Invoices — list
Design task D-14 · approved: Variant A — table first, mockup `design: Invoices — list · A` (#variant-a, #states-a) — chosen by the human's "Chosen variant" comment · not chosen, never built: `design: Invoices — list · B` · design system Harbor base v3 + web layer v1

## Screen map
375: title row (Invoices · New invoice) → search → status chips (scroll sideways) → invoice rows → "Load more"
1440: sidebar 240px | content: title row → search + chips in one row → table (Customer, Number, Issued, Due, Amount, Status) → pagination

## Components
| Element | Component | Variant / props | |
|---|---|---|---|
| New invoice | atoms/Button | variant primary, size md, icon Plus | existing |
| Search | molecules/SearchField | placeholder "Customer or invoice number" | existing |
| Status | atoms/Badge | paid → success, overdue → destructive, draft → muted; always with its text | existing |
| Invoice row (375) | molecules/InvoiceRow | customer + number left; amount + status right; due date below | NEW · molecule · states: default, pressed, focus-visible |

## Tokens
colour: background, surface (table header), foreground, muted-foreground (secondary lines), border, primary/on-primary, destructive (overdue) · type: heading-2 (title), body, body-sm (secondary), tabular numbers for amounts · space: 4 (375 page padding), 6 (1440), 3 (row padding) · radius: md · shadow: none — rows are separated by border

## States
- Loading: six skeleton rows in the row's shape; title, search and New invoice stay visible.
- Empty, first use: "No invoices yet" · "Create your first invoice and send it in under a minute." · primary "New invoice".
- Empty, no match: "No invoices match "{query}"" · ghost "Clear search".
- Error: banner above the list: "Invoices couldn't load. Check your connection and try again." · "Retry"; search and chips keep their values.
- Row: hover (1440) surface background; focus-visible 2px ring inset; pressed (375) surface background.
- Dark: tokens only, no per-component overrides.

## Responsive
| Width | Behaviour |
|---|---|
| < 640 (375) | rows, chips scroll sideways, "Load more" instead of pagination |
| 768 | table: Customer (number below), Amount, Status |
| 1024 | full table; sidebar collapses to icons |
| ≥ 1280 (1440) | full table; sidebar 240px; content max 1200px |

## Accessibility
- One h1 "Invoices"; the table has a visually hidden caption and column headers.
- Status is text + colour, never colour alone. Each row is one link named "<customer>, invoice <number>".
- Focus order: search → chips → New invoice → rows → pagination. Touch targets ≥ 44px at 375.
- Checked contrast: muted-foreground/background 6.06:1 · on-primary/primary 7.52:1 (light), 7.17:1 (dark).
- The result count after a search is announced politely.

## Copy
| Where | Text |
|---|---|
| title | Invoices |
| primary action | New invoice |
| search placeholder | Customer or invoice number |
| chips | All · Draft · Sent · Overdue · Paid |

## Out of scope
Bulk actions, CSV export, the invoice detail page.

Read the full file on GitHub · 95 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 95 lines · 51 tokens per session scan A 1f88c1bec0ec

Subscribe to this mod's changes

design-handoff-spec is a skill published in the GitHub repository makifbaysal/tasktrooper (113 stars, last pushed yesterday), licensed Apache-2.0. It adds 51 tokens to every session and 1,565 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-09.

Related

Other skills, from other repositories

wireframe

Produce low-fidelity black-and-white UI wireframes as SVGs or viewer pages. Use when asked to wireframe, sketch a screen, draft a layout, make a low-fi mockup, or publish wireframes.

paperclipai/paperclip · 47 tokens

design-critique

Give a structured product design critique — user job clarity, hierarchy, affordance, error states, accessibility, and consistency — focused on what to change, in what order, and why.

paperclipai/paperclip · 42 tokens

paperclip-capsules

Generate, implement, or review Paperclip capsule visuals. Use for capsule art, agent capsules, heartbeat status capsules, identicons, capsule banks, or brand-usage validation.

paperclipai/paperclip · 41 tokens

presentation-template-designer

Plan reusable presentation templates from a creative brief, optional brand assets, or an existing deck. Use when Codex needs to define a slide inventory, choose an editable presentation toolchain, author or validate a template manifest, adapt a visual system for PowerPoint or Google Slides, or prepare a reviewed…

Prompthon-IO/agent-systems-handbook · 70 tokens

design-before-build-gate

Enforces a design/spec approval gate before production implementation. Use when UI, UX, product flows, architecture, API shape, prototypes, visual direction, or user-facing behaviour need signoff before builders write production code.

joelbrilliant/agentic-delivery-skills · 49 tokens

architecture-design

Use this skill to design system architecture with documented trade-offs and decisions before any implementation begins. Activates when a feature, system, or component requires non-trivial structural decisions about how components interact, what data stores to use, or how to decompose a problem.

karthikrshet/aiskills · 60 tokens